Method for performing in-memory hash join processing in relational database systems
AssigneeTeradata US, Inc.
InventorsBhashyam Ramesh, Sai Pavan Kumar Pakala, Jaiprakash G Chimanchode
Life of this patent
Estimating the term…
Abstract
A method for performing in-memory hash join processing. This method utilizes bulk processing within the hash join steps, such as performing bulk reads of hash values from tables to be joined, and performing bulk probes of hash values in tables to be joined, thereby providing more efficient utilization of memory bandwidth and CPU throughput, reducing memory accesses in the execution path, and reducing CPU cycles per instruction. Data movement is reduced by reducing load-stores to memory and by performing more operations in CPU cache.
Claims12
A method for performing a hash join between an inner table and an outer table in a distributed relational database system, the method comprising the steps:
- reading a plurality of hash values from said outer table;
- probing said plurality of hash values in said inner table;
- producing a set of successfully probed outer table row ids;
- reading outer table rows corresponding to said outer table row ids;
- evaluating at least one join condition on said outer table rows corresponding to said outer table row ids in bulk;
- and
- building a result set of successfully evaluated outer table rows.
A method for performing a hash join between an inner table and an outer table in a distributed relational database system, the method comprising the steps:
- performing a bulk read of hash values from said outer table;
- performing a bulk probe of said hash values in said inner table;
- producing a set of successfully probed outer table row ids;
- reading outer table rows corresponding to said outer table row ids;
- evaluating at least one join condition for said outer table rows corresponding to said outer table row ids in bulk;
- and
- producing a result set containing successfully evaluated outer table rows.
Dependencies are inferred from the claim text.